Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94969
    Prev
    Next
    INDEX
    Explanations

    ask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Queue
    -0.08
    川県
    -0.08
    _queue
    -0.08
     innan
    -0.08
    .rand
    -0.08
     renowned
    -0.08
     Engineers
    -0.08
     bede
    -0.08
    assium
    -0.07
     Nazar
    -0.07
    POSITIVE LOGITS
     extracting
    0.09
     extraction
    0.09
    extract
    0.09
    Extract
    0.09
     asked
    0.09
     extracted
    0.08
     factual
    0.08
     question
    0.08
     Extract
    0.08
     질문
    0.08
    Activations Density 0.037%

    No Known Activations